CN116914751A - Intelligent power distribution control system - Google Patents
Intelligent power distribution control system Download PDFInfo
- Publication number
- CN116914751A CN116914751A CN202311168052.5A CN202311168052A CN116914751A CN 116914751 A CN116914751 A CN 116914751A CN 202311168052 A CN202311168052 A CN 202311168052A CN 116914751 A CN116914751 A CN 116914751A
- Authority
- CN
- China
- Prior art keywords
- sub
- power supply
- area
- node
- fuzzy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 64
- 230000006870 function Effects 0.000 claims description 51
- 238000005457 optimization Methods 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 21
- 230000002068 genetic effect Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 8
- 239000002243 precursor Substances 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 4
- 239000002699 waste material Substances 0.000 abstract 1
- 238000007726 management method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000035772 mutation Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
- H02J3/144—Demand-response operation of the power transmission or distribution network
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
- H02J2310/56—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads characterised by the condition upon which the selective controlling is based
- H02J2310/58—The condition being electrical
- H02J2310/60—Limiting power consumption in the network or in one section of the network, e.g. load shedding or peak shaving
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an intelligent power distribution control system, relates to the technical field of power distribution control, and aims to improve the power supply quality and the electric energy utilization rate of a power system. The system comprises a data acquisition part, a target area dividing part, a prediction part, a fuzzy topology establishing part, a conflict resolving part, a line optimizing part and a power distribution control part, wherein the parts cooperate to realize intelligent power distribution control of the power system based on a load prediction model, a fuzzy logic algorithm, a multi-target optimizing model and a power supply route planning model based on a shortest path algorithm. The method can effectively reduce the power supply cost and energy waste of the power system and improve the stability and reliability of the power system.
Description
Technical Field
The invention relates to the technical field of power distribution control, in particular to an intelligent power distribution control system.
Background
With the development of social economy and the increase of power demand, the safety, reliability and economy of power distribution systems are increasingly gaining importance. Conventional power distribution systems generally have problems of insufficient capacity, ageing of power lines, unbalanced power loads, frequent power faults and the like, and the problems bring great challenges to the operation and management of the power system. In view of these problems, various solutions have been proposed, in which an intelligent power distribution control system is an emerging technology, and has been widely used in the field of power distribution.
Before an intelligent power distribution control system, the traditional power distribution system mainly relies on manual operation and timing control, and the mode is low in efficiency, easy to cause misoperation and potential safety hazard, and cannot realize fine management and dynamic control on power loads. The intelligent power distribution control system can realize the fine management and dynamic control of the power load by utilizing the modern information technology and an intelligent control algorithm, and improves the safety, reliability and economy of the power distribution system.
Some intelligent power distribution control systems have been disclosed. For example, in an intelligent power distribution system based on a wireless sensor in the prior art, power load data is generally collected through the wireless sensor, and fine management and dynamic control on the power load are realized through cloud computing and an intelligent control algorithm. In addition, in the prior art, intelligent power distribution control systems based on distributed intelligent controllers are also available, and the systems generally realize distributed management and dynamic control of power loads through the distributed intelligent controllers, so that the stability and reliability of the power distribution system are improved.
Although these techniques have improved the management and control capabilities of power distribution systems to some extent, there are still problems in practical applications. First, there are still limitations to the processing and analysis of large-scale electrical load data, as the collection and processing techniques of electrical load data have not reached an ideal level. Secondly, the existing intelligent control algorithm still needs to be further optimized and perfected to achieve more refined power load management and control. In addition, the intelligent power distribution control system requires a great deal of cost for installing and maintaining hardware devices, which is also a great limiting factor for popularizing the intelligent power distribution control system.
In response to these problems, further research and exploration is needed to achieve a more efficient and reliable intelligent power distribution control system. On the one hand, research and development of a power load data acquisition and processing technology can be enhanced, and high-precision acquisition and analysis of the power load are realized by utilizing more advanced sensors and data processing algorithms, so that more accurate data support is provided for optimization and improvement of an intelligent power distribution control system. On the other hand, the intelligent control algorithm can be further researched and developed, and advanced technologies such as artificial intelligence, fuzzy control and the like are introduced into the intelligent power distribution control system, so that more refined management and dynamic control on the power load are realized.
Disclosure of Invention
The invention aims to provide an intelligent power distribution control system which can effectively improve the power supply quality and the power utilization rate of a power system and has higher practicability and economy.
In order to solve the above technical problems, the present invention provides an intelligent power distribution control system, including:
a data acquisition section configured to acquire data of a target power supply area and a target power system in one power supply period, to obtain historical load data and historical power supply total amount data;
A target area dividing section configured to divide a target power supply area into a plurality of sub-areas based on the acquired historical power supply total amount data, ensuring that a standard deviation of the historical power supply total amount in each sub-area is within a set threshold range; each sub-area corresponds to historical power supply total data of one sub-area and historical load data of one sub-area;
a prediction part configured to perform load prediction on each sub-area by using a preset load prediction model based on the historical load data of each sub-area, so as to obtain a load prediction result of each sub-area; based on the historical power supply total amount data of each sub-area, carrying out power supply total amount prediction on each sub-area by using a preset power supply total amount prediction model to obtain a power supply total amount prediction result of each sub-area;
the fuzzy topology establishment part is configured to consider each sub-area divided by the power supply area as a node, consider all power supply lines connected with each sub-area as a connecting line, and the target power system as a starting node to construct a fuzzy topology map;
the conflict resolution part is configured to optimize the power supply total amount prediction result of each sub-area by using a preset multi-objective optimization model based on the power supply total amount prediction result of each sub-area and the load prediction result of each sub-area to obtain an optimized electric quantity result of each sub-area;
The line optimization part is configured to calculate and obtain the shortest path between the target power supply system and each sub-area based on the constructed fuzzy topological graph;
and a power distribution control section configured to control the target power system, and to distribute the electric power for each of the sub-regions using a shortest path connected to each of the sub-regions, based on the optimized electric power result for each of the sub-regions.
Further, the load prediction model performs load prediction on each sub-area, and the method for obtaining the load prediction result of each sub-area includes: carrying out Gaussian blurring processing on the historical load data of each sub-area, and converting the historical load data into a group of load blurring amount; based on the historical load data of each sub-area, establishing a group of load fuzzy logic rule base according to expert experience or a machine learning mode; fuzzy reasoning is carried out according to the load fuzzy logic rule base, and a load fuzzy conclusion is obtained; and carrying out defuzzification treatment on the load fuzzy conclusion through a maximum membership method to obtain a load prediction result.
Further, the power supply total amount prediction model predicts the power supply total amount of each sub-area, and the method for obtaining the power supply total amount prediction result of each sub-area comprises the following steps: carrying out Gaussian blurring processing on the historical power supply total amount data of each sub-area, and converting the historical power supply total amount data into a group of power supply total amount blurring amounts; based on the historical power supply total amount data of each sub-area, a group of power supply total amount fuzzy logic rule base is established according to expert experience or a machine learning mode; fuzzy reasoning is carried out based on the fuzzy quantity of the total power supply and according to a fuzzy logic rule base of the total power supply, so as to obtain a fuzzy conclusion of the total power supply; and performing defuzzification treatment on the fuzzy conclusion of the total power supply through a maximum membership method to obtain a prediction result of the total power supply.
Further, when the power distribution control section distributes the power to each sub-area, the power distribution control section distributes the power to the sub-area in an amount equal to the optimized power result corresponding to the sub-area by using the shortest path between the sub-area and the target power system as a distribution line.
Further, the method for calculating the shortest path between the target power supply system and each sub-area based on the constructed fuzzy topological graph by the line optimization part comprises the following steps: the fuzzy topology map is expressed as:
：
wherein Is a node set comprising a target power supply system as a starting node and a sub-region as a node,is a collection of connection lines, corresponding to the connection lines;as a starting node, corresponding to a target power supply system;is a target node, corresponding to a sub-region;representing slave nodesTo the nodeDistance (or cost) of (a) a (b);to be from the initial nodeTo the nodeIs the shortest distance of (2);: from the initial nodeTo the nodeOn the shortest path of (a) a nodeIs a precursor node of (2); op is a node set to be expanded; cl is the extended node set; selecting a valuation function from op each timeThe minimum node is expanded; wherein,representing slave start nodesTo the nodeIs used for the shortest distance of (a), Representing slave nodesTo the target nodeIs a shortest distance estimate of (2); thus, the first and second substrates are bonded together,representing slave start nodesThrough the nodeTo the target nodeIs a shortest distance estimate of (2); initializing op and cl; order the，Will start the nodeAdding the mixture into an op; repeating the following steps until op is empty or a target node is found: step 1: selection from opMinimum nodeExpanding; step 2: node is connected withRemove from op and add it to cl; step 3: for nodesEach neighbor node of (a)If (3)Not in cl; step 4: calculation ofI.e. from the originating nodeThrough the nodeReach the nodeIs a distance of (2); step 5: if it isNot in op, willAdd op, and addA kind of electronic deviceThe value is set asThe method comprises the steps of carrying out a first treatment on the surface of the Step 6: if it isIn op, and newThe value is smaller than the original value, and the updating is performedA kind of electronic deviceAndvalue and willIs set as the precursor node ofThe method comprises the steps of carrying out a first treatment on the surface of the If the target node is foundThen pass throughBacktracking to the originating nodeObtaining the slaveTo the point ofIs the shortest path of (a);representing slave start nodesTo the nodeOn the shortest path of (a) a nodeIs a precursor node of (2); thus, it is able to passBacktracking to the originating nodeThe method comprises the steps of carrying out a first treatment on the surface of the The saidThe following conditions are satisfied:
；。
further, the valuation function is expressed using the following formula:
；
wherein ,for adjusting the coefficient, the value range is 0.2-0.8;andrespectively nodesAnd a target nodeCoordinates in the fuzzy topology map;is a valuation function.
Further, the conflict resolution portion includes: based on the power supply total amount prediction result of each sub-area and the load prediction result of each sub-area, optimizing the power supply total amount prediction result of each sub-area by using a preset multi-objective optimization model, and the method for obtaining the optimized power result of each sub-area comprises the following steps: assuming that there isEach subarea has a historical power supply total amount of respectivelyThe power supply total amount prediction result isThe method comprises the steps of carrying out a first treatment on the surface of the Calculating the difference between the total power supply amount and the load of each sub-area based on the historical total power supply amount data and the load prediction result of the sub-area, namely:
；
wherein ,in the form of a difference value,represent the firstThe total power supply amount prediction result of the sub-region,represent the firstThe load prediction results of the individual sub-areas,，is the number of subregions; defining an objective functionTo describe the optimization objective for all sub-regions,respectively obtaining intermediate values of electric quantity optimization results of each sub-area; solving an optimized electric quantity result by using a fuzzy multi-objective optimization algorithm; the input of the algorithm is an objective function And the upper and lower bounds of the optimized charge result for each sub-region, i.e, wherein Is the firstMaximum power supply capability of the sub-region; outputting optimized power results for each sub-region。
Further, the fuzzy multi-objective optimization algorithm is a genetic algorithm.
Further, the objective function consists of two parts: the first part is the error between the historical power supply total amount data and the power supply total amount prediction result of all the subareas, and the second part is the electric quantity balance among all the subareas; the two parts are described using a fuzzy logic function, the formula of which is as follows:
；
wherein ,andrespectively, is a fuzzy logic function, and the method comprises the steps of,andis a weight coefficient;the input of the power supply is the weighted sum of the difference between the optimized electric quantity result and the power supply total quantity prediction result of all the subareas, and the output is the error of the whole system;the input of the power balance degree is the difference between the maximum value and the minimum value of the optimized power results of all the subareas, and the output is the power balance degree of the whole system;representing an objective function.
Further, the fuzzy multi-objective optimization algorithm is an NSGA-II algorithm.
The intelligent power distribution control system has the following beneficial effects:
firstly, the invention adopts the fuzzy multi-objective optimization algorithm to realize the optimal distribution of the electric quantity, and can more accurately predict the load demand of each subarea, so that the electric power system can better ensure the stable operation of the electric power system while meeting the electric energy demand of each subarea. By analyzing the historical power supply total amount data and the load prediction result, the power supply total amount and load difference value of each sub-area can be obtained, and the power supply total amount and load difference value is used as a part of an objective function to be optimized and solved, so that the distribution efficiency of electric quantity is effectively improved, and the power supply quality of a power system is improved.
And secondly, the optimization target of each sub-area is measured by adopting the objective function based on the fuzzy logic function, so that the electric quantity balance degree and the error rate of each sub-area can be estimated more accurately, and the electric quantity distribution result which is more in line with the actual situation can be obtained. In the calculation process of the objective function, the invention also uses the weighting coefficient to quantify the optimization target of each sub-area, thereby better controlling the electric quantity distribution result and further improving the power supply quality of the electric power system.
In addition, the invention also adopts the shortest path algorithm based on the fuzzy topological graph to carry out the power distribution control of the power system, and the algorithm can effectively reduce the power supply loss of the power system and improve the utilization efficiency of electric energy. By using the fuzzy topological graph, the invention can accurately describe the power relation of each subarea in the power system, find the shortest path between each subarea and the target power system, further improve the transmission efficiency of electric energy and reduce the power supply loss.
Finally, the invention also adopts an intelligent decision technology and a conflict resolution technology, can realize intelligent electric quantity distribution and distribution control, and improves the self-adaption capability and robustness of the power system. When the power system is abnormal or the load demand changes, the invention can timely adjust and optimize, ensure the stable operation of the power system and improve the stability and safety of the power system.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only embodiments of the invention and that other drawings can be obtained according to the drawings provided without inventive effort for a person skilled in the art.
Fig. 1 is a schematic system structure diagram of an intelligent power distribution control system according to an embodiment of the present invention.
Detailed Description
The core of the invention is to provide an intelligent power distribution control system which can more accurately predict the power supply quantity and load, effectively avoid the occurrence of unbalance of the supply and the demand and improve the stability and the reliability of a power system. The method of the invention can be applied to not only the traditional centralized power system, but also the distributed energy system, such as photovoltaic power generation, wind power generation and the like.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, an intelligent power distribution control system, the system comprising:
a data acquisition section configured to acquire data of a target power supply area and a target power system in one power supply period, to obtain historical load data and historical power supply total amount data;
specifically, the part includes the following processes in the execution process:
a target power supply area and a target power system are determined. In practical application, a target power supply area and a target power system which need to be intelligently controlled in power distribution can be determined according to specific requirements and actual conditions.
And configuring a data acquisition device. According to the specific conditions of the target power supply area and the target power system, corresponding data acquisition equipment such as a sensor, an electric energy meter, a monitoring system and the like can be configured for acquiring historical load data and historical power supply total amount data.
And acquiring data in real time. The data acquisition equipment can acquire related data of the target power supply area and the target power system in real time, and transmits the data to the data acquisition part for processing. In each power supply period, the data acquisition section acquires data of the target power supply area and the target power system in the period.
And processing the data. The data acquisition part processes and analyzes the acquired historical load data and the historical power supply total amount data to obtain related data of the target power supply area and the target power system. The historical load data can reflect the electricity consumption condition of the target power supply area, and the historical power supply total amount data can reflect the power supply condition of the target power supply area.
The data is stored. The data acquisition portion stores the processed data in a database or other data storage device for subsequent analysis and processing.
A target area dividing section configured to divide a target power supply area into a plurality of sub-areas based on the acquired historical power supply total amount data, ensuring that a standard deviation of the historical power supply total amount in each sub-area is within a set threshold range; each sub-area corresponds to historical power supply total data of one sub-area and historical load data of one sub-area;
specifically, the execution of the part specifically includes the following processes:
historical power supply total amount data is determined. The target area dividing section needs to acquire the historical power supply total amount data, which can be obtained from the data acquiring section, first. A partitioning standard deviation threshold is determined. According to the actual situation, the target area dividing part needs to set a standard deviation threshold value so as to ensure that the standard deviation of the historical power supply total amount in each sub-area is within the set threshold value range.
And (5) dividing the area. The target area dividing part divides the target power supply area into a plurality of subareas, and ensures that the standard deviation of the historical power supply total amount in each subarea is within a set threshold range. The specific partitioning method can adopt a clustering analysis-based method, such as a k-means algorithm, a DBSCAN algorithm and the like, and can also adopt other algorithms such as a divide-and-conquer method and the like.
Historical power supply total amount data and historical load data of the subareas are determined. The target area dividing section performs statistics and analysis on the historical power supply total amount data of each sub-area, and obtains the historical power supply total amount data and the historical load data of each sub-area.
The sub-region data is stored. The target area dividing section stores the historical power supply aggregate data and the historical load data for each sub-area in a database or other data storage device for subsequent analysis and processing.
A prediction part configured to perform load prediction on each sub-area by using a preset load prediction model based on the historical load data of each sub-area, so as to obtain a load prediction result of each sub-area; based on the historical power supply total amount data of each sub-area, carrying out power supply total amount prediction on each sub-area by using a preset power supply total amount prediction model to obtain a power supply total amount prediction result of each sub-area;
The fuzzy topology establishment part is configured to consider each sub-area divided by the power supply area as a node, consider all power supply lines connected with each sub-area as a connecting line, and the target power system as a starting node to construct a fuzzy topology map;
the conflict resolution part is configured to optimize the power supply total amount prediction result of each sub-area by using a preset multi-objective optimization model based on the power supply total amount prediction result of each sub-area and the load prediction result of each sub-area to obtain an optimized electric quantity result of each sub-area;
the line optimization part is configured to calculate and obtain the shortest path between the target power supply system and each sub-area based on the constructed fuzzy topological graph;
and a power distribution control section configured to control the target power system, and to distribute the electric power for each of the sub-regions using a shortest path connected to each of the sub-regions, based on the optimized electric power result for each of the sub-regions.
Example 2
On the basis of the above embodiment, the method for obtaining the load prediction result of each sub-area by using the load prediction model to perform load prediction on each sub-area includes: carrying out Gaussian blurring processing on the historical load data of each sub-area, and converting the historical load data into a group of load blurring amount; based on the historical load data of each sub-area, establishing a group of load fuzzy logic rule base according to expert experience or a machine learning mode; fuzzy reasoning is carried out according to the load fuzzy logic rule base, and a load fuzzy conclusion is obtained; and carrying out defuzzification treatment on the load fuzzy conclusion through a maximum membership method to obtain a load prediction result.
Specifically, the execution of the load prediction model specifically includes the following procedures:
and (5) Gaussian blurring processing. The historical load data of each sub-region is processed through Gaussian blurring, and is converted into a group of load blurring amount. The Gaussian blur processing can enable the historical load data to be smoother, so that the influence of abnormal values is reduced, and the accuracy of load prediction is improved.
Is provided withRepresent the firstThe number of data of the historical load,represent the firstThe number of fuzzy sets is chosen such that,representation ofAt fuzzy aggregationThe membership degree in (c) is the formula of fuzzification input:
；
wherein ,andrespectively represent fuzzy setsAnd standard deviation of the center of (c).
And establishing a load fuzzy logic rule base. Based on the historical load data of each sub-region, a set of load fuzzy logic rule base can be established according to expert experience or a machine learning mode. The rule base includes a series of fuzzy rules, each describing a fuzzy relationship between load and a number of related factors.
The following is an example of a simple fuzzy logic rule base in which the input variables are the precedingThe historical load data of the hour, the output variable is the load predicted value of the next moment:
if the current load is low and the front load is low The load data for an hour is at a lower level and then the load predictor at the next moment is at a low level.
If the current load is low and the front load is lowThe load data for an hour is at a higher level and then the load prediction value for the next moment is at a medium level.
If the current load is at a medium level, and frontThe load data for an hour is at a lower level and then the load forecast for the next moment is at a medium level.
If the current load is at a medium level, and frontThe load data for an hour is at a medium level, and then the load predicted value for the next time is at a medium level.
If the current load is at a medium level, and frontThe load data for an hour is at a higher level, and then the load predicted value for the next moment is at a high level.
If the current load is high, and the frontThe load data for an hour is at a lower level and then the load forecast for the next moment is at a medium level.
If the current load is high, and the frontThe load data for an hour is at a medium level, and then the load predicted value for the next time is at a high level.
If the current load is high, and the frontThe load data for an hour is at a higher level, and then the load predicted value for the next moment is at a high level.
Fuzzy reasoning. And carrying out fuzzy reasoning according to the load fuzzy logic rule base to obtain a load fuzzy conclusion. The fuzzy inference is to perform fuzzy calculation on the input data according to the fuzzy logic rule base so as to obtain a fuzzy output result.
And matching the rules in the fuzzy logic rule base with the fuzzified historical load data to obtain a fuzzy conclusion. Here, it is assumed that fuzzy reasoning is performed using a fuzzy maximum composition algorithm. Let the fuzzy conclusion beThe formula is:
；
wherein ,the minimum value is represented by the minimum value,representing a maximum value.Representing the membership of the future load data and the historical load data in the corresponding fuzzy sets, respectively. Setting up common in fuzzy logic rule baseBar rule, firstThe precondition of the bar rule is thatThe rear part is divided intoThe calculation formula of the fuzzy conclusion is:
；
and (5) deblurring. And carrying out defuzzification treatment on the load fuzzy conclusion through a maximum membership method to obtain a load prediction result. The maximum membership method is a common fuzzy reasoning method, and the basic idea is to find the element with the maximum membership in the fuzzy set as an output result.
And converting the fuzzy conclusion into an actual load prediction result. Common defuzzification methods include maximum membership, averaging, weighted averaging, and the like. Here, assuming that the maximum membership method is adopted for the defuzzification processing, the load prediction result is:
wherein ,representation and rendering ofAt the time of taking maximum valueValues.
The maximum membership method is a common fuzzy logic method for processing fuzzy or uncertainty information. The basic idea of the method is to match the input fuzzy amount (e.g. fuzzy linguistic variables) with a set of fuzzy subsets, thereby obtaining a set of membership values describing the degree to which the input fuzzy amount belongs to each fuzzy subset. In the maximum membership method, the determination of the output value is based on the subset with the largest membership value, i.e. the output value is equal to the output value of the subset with the largest membership value. The method can be effectively applied to the fields of fuzzy control, fuzzy decision and the like, can improve the robustness and fault tolerance of the system, and has stronger practicability and reliability. In the invention, the maximum membership method is used for processing fuzzy information such as load prediction, power supply total amount prediction and the like and optimizing electric quantity result distribution, thereby improving the power supply quality and the electric energy utilization rate of the electric power system and having higher practical application value.
Example 3
On the basis of the above embodiment, the method for predicting the total power supply amount of each sub-area by using the total power supply amount prediction model to obtain the total power supply amount prediction result of each sub-area includes: carrying out Gaussian blurring processing on the historical power supply total amount data of each sub-area, and converting the historical power supply total amount data into a group of power supply total amount blurring amounts; based on the historical power supply total amount data of each sub-area, a group of power supply total amount fuzzy logic rule base is established according to expert experience or a machine learning mode; fuzzy reasoning is carried out based on the fuzzy quantity of the total power supply and according to a fuzzy logic rule base of the total power supply, so as to obtain a fuzzy conclusion of the total power supply; and performing defuzzification treatment on the fuzzy conclusion of the total power supply through a maximum membership method to obtain a prediction result of the total power supply.
Specifically, the power supply total amount prediction model uses a method similar to the load prediction model, and specifically comprises the following steps:
and (5) Gaussian blurring processing. And carrying out Gaussian blurring processing on the historical power supply total amount data of each sub-area, and converting the historical power supply total amount data into a group of power supply total amount blurring amounts. The Gaussian blurring process can enable the historical power supply total amount data to be smoother, so that the influence of abnormal values is reduced, and the accuracy of power supply total amount prediction is improved.
And establishing a fuzzy logic rule base of the total power supply. Based on the historical power supply total amount data of each sub-area, a group of power supply total amount fuzzy logic rule base can be established according to expert experience or a machine learning mode. The rule base includes a series of fuzzy rules, each describing a fuzzy relationship between the total amount of power supplied and some relevant factor.
Fuzzy reasoning. And carrying out fuzzy reasoning according to the fuzzy logic rule base of the total power supply quantity to obtain a fuzzy conclusion of the total power supply quantity. The fuzzy inference is to perform fuzzy calculation on the input data according to the fuzzy logic rule base so as to obtain a fuzzy output result.
And (5) deblurring. And performing defuzzification treatment on the fuzzy conclusion of the total power supply through a maximum membership method to obtain a prediction result of the total power supply. The maximum membership method is a common fuzzy reasoning method, and the basic idea is to find the element with the maximum membership in the fuzzy set as an output result.
Example 4
On the basis of the above embodiment, when the power distribution control section distributes the electric power for each sub-area, the power distribution control section distributes the electric power of the amount equal to the optimized electric power result corresponding to the sub-area using the shortest path between the sub-area and the target power system as the distribution line.
Specifically, the power distribution control section controls the target power system to distribute the equal amount of power to each sub-region based on the optimized power result of the sub-region and the shortest path between the sub-region and the target power system. Specifically, the part distributes the corresponding electric quantity to the subarea according to the shortest path according to the optimized electric quantity result so as to meet the electric power requirement of the subarea.
Example 5
On the basis of the above embodiment, the method for calculating the shortest path between the target power supply system and each sub-area by the line optimization part based on the constructed fuzzy topological graph includes: the fuzzy topology map is expressed as:
：
wherein Is a node set comprising a target power supply system as a starting node and a sub-region as a node,is a collection of connection lines, corresponding to the connection lines;as a starting node, corresponding to a target power supply system; Is a target node, corresponding to a sub-region;representing slave nodesTo the nodeDistance (or cost) of (a) a (b);to be from the initial nodeTo the nodeIs the shortest distance of (2);: from the initial nodeTo the nodeOn the shortest path of (a) a nodeIs a precursor node of (2); op is a node set to be expanded; cl is the extended node set; selecting a valuation function from op each timeThe minimum node is expanded; wherein,representing slave start nodesTo the nodeIs used for the shortest distance of (a),representing slave nodesTo the target nodeIs a shortest distance estimate of (2); thus, the first and second substrates are bonded together,representing slave start nodesThrough the nodeTo the target nodeIs a shortest distance estimate of (2); initializing op and cl; order the，Will start the nodeAdding the mixture into an op; repeating the following steps until op is empty or a target node is found: step 1: selection from opMinimum nodeExpanding; step 2: node is connected withRemove from op and add it to cl; step 3: for nodesEach neighbor node of (a)If (3)Not in cl; step 4: calculation ofI.e. from the originating nodeThrough the nodeReach the nodeIs a distance of (2); step 5: if it isNot in op, willAdd op, and addA kind of electronic deviceThe value is set asThe method comprises the steps of carrying out a first treatment on the surface of the Step 6: if it is In op, and newThe value is smaller than the original value, and the updating is performedA kind of electronic deviceAndvalue and willIs set as the precursor node ofThe method comprises the steps of carrying out a first treatment on the surface of the If the target node is foundThen pass throughBacktracking to the startNodeObtaining the slaveTo the point ofIs the shortest path of (a);representing slave start nodesTo the nodeOn the shortest path of (a) a nodeIs a precursor node of (2); thus, it is able to passBacktracking to the originating nodeThe method comprises the steps of carrying out a first treatment on the surface of the The saidThe following conditions are satisfied:
；。
example 6
On the basis of the above embodiment, the valuation function is expressed using the following formula:
；
wherein ,for adjusting the coefficient, the value range is 0.2-0.8;andrespectively nodesAnd a target nodeCoordinates in the fuzzy topology map;is a valuation function.
Specifically, the valuation functionIs a multiple function that includes the effects of a number of factors. Wherein the first itemRepresenting a starting nodeTo the nodeDistance of the second termRepresenting nodesAnd a target nodeEuclidean distance between them. Adjustment coefficientThe range of the values is as followsCan be adjusted according to actual conditions.
In the first itemRepresenting a starting nodeTo the nodeIs used for the distance of (a),representing nodesTo the target nodeIs used to determine the estimated value of the shortest distance,is thatIs used to determine the number of pairs of values,is thatIs a numerical value of (a). The logarithmic sum index is used herein to give The sensitivity of the function is increased when the value is smaller. By such design, the valuation function can be applied to the nodeTo the target nodeHas better adaptability and sensitivity.
Second item representationEuclidean distance, a nodeAnd a target nodeGeometric distance between them. By adding the Euclidean distance into the valuation function, the algorithm can consider the geometric position relation among the nodes, and the accuracy and the reliability of path planning are further improved.
In general, the valuation function integrates a number of factors into a nodeTo the target nodeIs a relatively comprehensive and efficient valuation function.
Example 7
On the basis of the above embodiment, the conflict resolution portion includes: based on the power supply total amount prediction result of each sub-area and the load prediction result of each sub-area, optimizing the power supply total amount prediction result of each sub-area by using a preset multi-objective optimization model, and the method for obtaining the optimized power result of each sub-area comprises the following steps: assuming that there isEach subarea has a historical power supply total amount of respectivelyThe power supply total amount prediction result isThe method comprises the steps of carrying out a first treatment on the surface of the Calculating the difference between the total power supply amount and the load of each sub-area based on the historical total power supply amount data and the load prediction result of the sub-area, namely:
；
wherein ,in the form of a difference value,represent the firstThe total power supply amount prediction result of the sub-region,represent the firstThe load prediction results of the individual sub-areas,，is the number of subregions; defining an objective functionTo describe the optimization objective for all sub-regions,respectively obtaining intermediate values of electric quantity optimization results of each sub-area; solving an optimized electric quantity result by using a fuzzy multi-objective optimization algorithm; the input of the algorithm is an objective functionAnd the upper and lower bounds of the optimized charge result for each sub-region, i.e, wherein Is the firstMaximum power supply capability of the sub-region; outputting optimized power results for each sub-region。
Example 8
On the basis of the above embodiment, the fuzzy multi-objective optimization algorithm is a genetic algorithm.
Specifically, the genetic algorithm is used as a fuzzy multi-objective optimization algorithm for optimizing the electric quantity result of each sub-area. The process of the genetic algorithm can be summarized as the following steps:
initializing a population: a set of initial individuals is randomly generated as a population, each individual representing the electrical outcome of a set of sub-regions.
Evaluating fitness: for each individual, calculating the fitness value according to the objective function, and measuring the quality of the individual.
Selection operation: and selecting individuals with high fitness from the population as parents, and generating next generation individuals through selection operation.
Crossover operation: for the selected parent individuals, a crossover operation is performed to produce new offspring individuals.
Mutation operation: and carrying out mutation operation on the newly generated offspring individuals to increase the diversity of the population.
Evaluating fitness: fitness evaluation is performed on newly generated offspring individuals.
Determining a next generation population: and determining the next generation population according to the new individuals generated by the selection, crossing and mutation operations.
Termination condition: and when the preset iteration times are reached or a certain convergence condition is met, stopping the algorithm and returning to the optimal solution.
In the present invention, individuals of the genetic algorithm represent the optimized power results for each sub-region, and populations represent all possible sub-region power combinations. And optimizing the electric quantity result of each sub-area through a genetic algorithm, and optimizing the electric quantity result of each sub-area. The power grid loss can be reduced to the maximum extent while the power supply requirement is met to the maximum extent.
When a genetic algorithm is used, the objective function is an objective function for optimizing the power balance and the power utilization efficiency of the whole system in consideration of the error between the optimized power of each sub-region and the predicted result of the total power supply amount and the power balance between all sub-regions, and can be expressed as:
；
Is the intermediate value of the optimized electric quantity result of each sub-area, and after the objective function is solved by using a genetic algorithm, the output result is thatA value, as an optimized charge result for each sub-region,is the firstThe difference between the total amount of power supplied and the load in the sub-area.Andthe weight coefficients of the error and the electric quantity balance in the objective function are set according to actual conditions and requirements.
Example 9
On the basis of the above embodiment, the objective function consists of two parts: the first part is the error between the historical power supply total amount data and the power supply total amount prediction result of all the subareas, and the second part is the electric quantity balance among all the subareas; the two parts are described using a fuzzy logic function, the formula of which is as follows:
；
wherein ,andrespectively, is a fuzzy logic function, and the method comprises the steps of,andis a weight coefficient;the input of the power supply is the weighted sum of the difference between the optimized electric quantity result and the power supply total quantity prediction result of all the subareas, and the output is the error of the whole system;the input of the power balance degree is the difference between the maximum value and the minimum value of the optimized power results of all the subareas, and the output is the power balance degree of the whole system; Representing an objective function.
In particular, in this embodiment, the objective function consists of two parts, namely the error between the historical total power supply data and the total power supply prediction result and the power balance between all the sub-areas. Both parts are represented as fuzzy logic functions to better handle fuzzy and uncertain information.
Fuzzy logic function of the first partThe input of the power supply is the weighted sum of the difference between the optimized power quantity result and the power supply total quantity prediction result of all the subareas, and the output is the error of the whole system. The form of the function can be Gaussian, triangular or trapezoidal, and the specific form can be selected and adjusted according to actual conditions.
Fuzzy logic function of the second partThe input of the system is the difference between the maximum value and the minimum value of the optimized electric quantity results of all the subareas, and the output is the electric quantity balance degree of the whole system. Likewise, the form of this function may also be gaussian, triangular or trapezoidal, etc.
Weighting coefficients of the two partsAndcan be adjusted according to actual conditions so as to achieve the effect of optimizing the system. For example, if more emphasis is placed on maintaining the power balance of the system, the power balance may be increased Weights of (2); if more emphasis is placed on reducing errors, the method can increaseIs a weight of (2).
The whole objective function is very flexible in form and can be adjusted and optimized according to actual conditions. By using fuzzy logic functions to represent the uncertainty and ambiguity of the objective function, this complex optimization problem can be better addressed.
Example 10
On the basis of the above embodiment, the fuzzy multi-objective optimization algorithm is an NSGA-II algorithm.
NSGA-II (Non-dominated Sorting Genetic Algorithm II) is a commonly used multi-objective optimization algorithm, which is an evolutionary algorithm based on genetic algorithms, and is mainly used for solving the complex problem of multiple decision variables and objective functions. The algorithm maintains diversity and balance of the population by performing non-dominant ranking and crowding distance calculation on individuals, thereby enabling the algorithm to reach Pareto optimal solution sets among multiple targets.
The basic idea of NSGA-II algorithms is to divide individuals in a population into a number of levels according to a non-dominant ranking, the higher the level the better the individuals are, and then to maintain diversity and balance by calculating the crowded distance between the individuals and surrounding individuals. Specifically, the algorithm first generates a new offspring population through operations such as crossover and mutation, and then merges the parent population and offspring population into a large population. The algorithm then non-dominantly sorts the population to determine the Pareto front level each individual is at. After ranking, the algorithm calculates the crowding distance around each individual and uses the crowding distance selection operator to select the better individual and generate the next generation population.
In this embodiment, the NSGA-II algorithm is used to perform fuzzy multi-objective optimization to obtain an optimized power result for each sub-region by minimizing two fuzzy logic functions in the objective function. Because NSGA-II algorithm has the characteristics of high efficiency and stability, the method is widely applied to the treatment of multi-objective optimization problems.
The present invention has been described in detail above. The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present invention and its core ideas. It should be noted that it would be obvious to those skilled in the art that various improvements and modifications can be made to the present invention without departing from the principle of the present invention, and these improvements and modifications fall within the scope of the claims of the present invention.
Claims (10)
1. An intelligent power distribution control system, the system comprising:
a data acquisition section configured to acquire data of a target power supply area and a target power system in one power supply period, to obtain historical load data and historical power supply total amount data;
a target area dividing section configured to divide a target power supply area into a plurality of sub-areas based on the acquired historical power supply total amount data, ensuring that a standard deviation of the historical power supply total amount in each sub-area is within a set threshold range; each sub-area corresponds to historical power supply total data of one sub-area and historical load data of one sub-area;
A prediction part configured to perform load prediction on each sub-area by using a preset load prediction model based on the historical load data of each sub-area, so as to obtain a load prediction result of each sub-area; based on the historical power supply total amount data of each sub-area, carrying out power supply total amount prediction on each sub-area by using a preset power supply total amount prediction model to obtain a power supply total amount prediction result of each sub-area;
the fuzzy topology establishment part is configured to consider each sub-area divided by the power supply area as a node, consider all power supply lines connected with each sub-area as a connecting line, and the target power system as a starting node to construct a fuzzy topology map;
the conflict resolution part is configured to optimize the power supply total amount prediction result of each sub-area by using a preset multi-objective optimization model based on the power supply total amount prediction result of each sub-area and the load prediction result of each sub-area to obtain an optimized electric quantity result of each sub-area;
the line optimization part is configured to calculate and obtain the shortest path between the target power supply system and each sub-area based on the constructed fuzzy topological graph;
And a power distribution control section configured to control the target power system, and to distribute the electric power for each of the sub-regions using a shortest path connected to each of the sub-regions, based on the optimized electric power result for each of the sub-regions.
2. The system of claim 1, wherein the load prediction model performs load prediction on each sub-region, and the method for obtaining the load prediction result of each sub-region comprises: carrying out Gaussian blurring processing on the historical load data of each sub-area, and converting the historical load data into a group of load blurring amount; based on the historical load data of each sub-area, establishing a group of load fuzzy logic rule base according to expert experience or a machine learning mode; fuzzy reasoning is carried out according to the load fuzzy logic rule base, and a load fuzzy conclusion is obtained; and carrying out defuzzification treatment on the load fuzzy conclusion through a maximum membership method to obtain a load prediction result.
3. The system of claim 1, wherein the power supply total amount prediction model predicts the power supply total amount for each sub-area, and the method for obtaining the power supply total amount prediction result for each sub-area comprises: carrying out Gaussian blurring processing on the historical power supply total amount data of each sub-area, and converting the historical power supply total amount data into a group of power supply total amount blurring amounts; based on the historical power supply total amount data of each sub-area, a group of power supply total amount fuzzy logic rule base is established according to expert experience or a machine learning mode; fuzzy reasoning is carried out based on the fuzzy quantity of the total power supply and according to a fuzzy logic rule base of the total power supply, so as to obtain a fuzzy conclusion of the total power supply; and performing defuzzification treatment on the fuzzy conclusion of the total power supply through a maximum membership method to obtain a prediction result of the total power supply.
4. A system according to claim 2 or 3, wherein the distribution control section, when distributing the electric power for each sub-area, distributes the electric power of the optimized electric power result equivalent to the sub-area using the shortest path of the sub-area and the target electric power system as the distribution line.
5. The system of claim 4, wherein the line optimization section calculates a shortest path between the target power supply system and each sub-area based on the constructed fuzzy topology, the method comprising: the fuzzy topology map is expressed as:
：
wherein Is a node set comprising a target power supply system as a starting node and a sub-area as a node +.>Is a collection of connection lines, corresponding to the connection lines; is provided with->As a starting node, corresponding to a target power supply system; />Is a target node, corresponding to a sub-region; />Representing slave node->To node->Distance or cost of (a); />For->To node->Is the shortest distance of (2); />: from the start node->To node->Node +.>Is a precursor node of (2); op is a node set to be expanded; cl is the extended node set; selecting a valuation function from op each time +. >The minimum node is expanded; wherein (1)>Representing->To node->Is (are) shortest distance->Representing slave node->To the target node->Is a shortest distance estimate of (2); thus (S)>Representing->Through node->To the target node->Is a shortest distance estimate of (2); initializing op and cl; let->，/>Start node +.>Adding the mixture into an op; repeating the following steps until op is empty or the target node +.>：
Step 1: selection from opMinimum node->Expanding;
step 2: node is connected withRemove from op and add it to cl;
step 3: for nodesIs->If->Not in cl;
step 4: calculation ofI.e. from the start node->Through node->Reach node->Distance of (2)；
Step 5: if it isNot in op, will->Add op, and add->Is->The value is set to +.>；
Step 6: if it isIn op, and New +.>The value is smaller than the original value, and the +.>Is-> and />Value and will->Is set to +.>The method comprises the steps of carrying out a first treatment on the surface of the If the target node is found +.>By->Backtracking to the start node->Is obtained from->To->Is the shortest path of (a);
representing->To node->Node +.>Is a precursor node of (2); thus, it can pass- >Backtracking to the start node->The method comprises the steps of carrying out a first treatment on the surface of the Said->The following conditions are satisfied:
；/>。
6. the system of claim 5, wherein the valuation function is represented using the following formula:
；
wherein ,for adjusting the coefficient, the value range is 0.2-0.8; /> and />Respectively is node->And target node->Coordinates in the fuzzy topology map; />Is a valuation function.
7. The system of claim 6, wherein the conflict resolution portion comprises: based on the power supply total amount prediction result of each sub-area and the load prediction result of each sub-area, optimizing the power supply total amount prediction result of each sub-area by using a preset multi-objective optimization model, and the method for obtaining the optimized power result of each sub-area comprises the following steps: assuming that there isThe historical power supply total amount of each sub-area is +.>The power supply total amount prediction result isThe method comprises the steps of carrying out a first treatment on the surface of the Calculating the difference between the total power supply amount and the load of each sub-area based on the historical total power supply amount data and the load prediction result of the sub-area, namely:
；
wherein ,for difference->Indicate->Prediction result of total power supply of sub-area, +.>Indicate->Load prediction results for individual sub-regions, +.>，/>Is the number of subregions; defining an objective function +. >To describe the optimization objective of all sub-regions, +.>Respectively obtaining intermediate values of electric quantity optimization results of each sub-area; using fuzzy multi-objectAn optimization algorithm is used for solving an optimized electric quantity result; the input of the algorithm is the objective function +.>And the upper and lower bounds of the optimized charge result for each sub-region, i.e. +.>, wherein />Is->Maximum power supply capability of the sub-region; outputting the optimized power result +/for each sub-area>。
8. The system of claim 7, wherein the fuzzy multi-objective optimization algorithm is a genetic algorithm.
9. The system of claim 8, wherein the objective function consists of two parts: the first part is the error between the historical power supply total amount data and the power supply total amount prediction result of all the subareas, and the second part is the electric quantity balance among all the subareas; the two parts are described using a fuzzy logic function, the formula of which is as follows:
；
wherein , and />Respectively, fuzzy logic functions +.> and />Is a weight coefficient; />The input of the power supply is the weighted sum of the difference between the optimized electric quantity result and the power supply total quantity prediction result of all the subareas, and the output is the error of the whole system;the input of the power balance degree is the difference between the maximum value and the minimum value of the optimized power results of all the subareas, and the output is the power balance degree of the whole system; / >Representing an objective function.
10. The system of claim 7, wherein the fuzzy multi-objective optimization algorithm is an NSGA-II algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311168052.5A CN116914751B (en) | 2023-09-12 | 2023-09-12 | Intelligent power distribution control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311168052.5A CN116914751B (en) | 2023-09-12 | 2023-09-12 | Intelligent power distribution control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116914751A true CN116914751A (en) | 2023-10-20 |
| CN116914751B CN116914751B (en) | 2023-12-05 |
Family
ID=88360587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311168052.5A Active CN116914751B (en) | 2023-09-12 | 2023-09-12 | Intelligent power distribution control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116914751B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236663A (en) * | 2023-11-14 | 2023-12-15 | 深圳前海橙色魔方信息技术有限公司 | Computer data analysis method and system based on artificial intelligence |
| CN117424231A (en) * | 2023-12-14 | 2024-01-19 | 深圳市华星数字有限公司 | Energy-saving power distribution control system and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107104442A (en) * | 2017-04-20 | 2017-08-29 | 河海大学 | The computational methods of Probabilistic Load containing wind power plant of meter and parameter fuzzy |
| CN107706932A (en) * | 2017-09-18 | 2018-02-16 | 浙江大学 | A kind of energy method for optimizing scheduling based on dynamic self-adapting fuzzy logic controller |
| CN110443428A (en) * | 2019-08-12 | 2019-11-12 | 上海宝能信息科技有限公司 | A kind of air compressor group load forecasting method and its control equipment |
| CN112202168A (en) * | 2020-09-28 | 2021-01-08 | 国网江苏省电力有限公司苏州供电分公司 | Multi-element power grid advanced control power supply method and system based on multi-objective coordination optimization |
| CN115693652A (en) * | 2022-10-19 | 2023-02-03 | 贵州电网有限责任公司 | Power distribution network frame optimization method and device based on power balance and performance cost |
| CN116485075A (en) * | 2023-04-23 | 2023-07-25 | 国网江苏省电力有限公司南通市海门区供电分公司 | FTS-based power grid load prediction method |
| CN116646933A (en) * | 2023-07-24 | 2023-08-25 | 北京中能亿信软件有限公司 | Big data-based power load scheduling method and system |
-
2023
- 2023-09-12 CN CN202311168052.5A patent/CN116914751B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107104442A (en) * | 2017-04-20 | 2017-08-29 | 河海大学 | The computational methods of Probabilistic Load containing wind power plant of meter and parameter fuzzy |
| CN107706932A (en) * | 2017-09-18 | 2018-02-16 | 浙江大学 | A kind of energy method for optimizing scheduling based on dynamic self-adapting fuzzy logic controller |
| CN110443428A (en) * | 2019-08-12 | 2019-11-12 | 上海宝能信息科技有限公司 | A kind of air compressor group load forecasting method and its control equipment |
| CN112202168A (en) * | 2020-09-28 | 2021-01-08 | 国网江苏省电力有限公司苏州供电分公司 | Multi-element power grid advanced control power supply method and system based on multi-objective coordination optimization |
| CN115693652A (en) * | 2022-10-19 | 2023-02-03 | 贵州电网有限责任公司 | Power distribution network frame optimization method and device based on power balance and performance cost |
| CN116485075A (en) * | 2023-04-23 | 2023-07-25 | 国网江苏省电力有限公司南通市海门区供电分公司 | FTS-based power grid load prediction method |
| CN116646933A (en) * | 2023-07-24 | 2023-08-25 | 北京中能亿信软件有限公司 | Big data-based power load scheduling method and system |
Non-Patent Citations (1)
| Title |
|---|
| 曾鸣;杜楠;张鲲;周飞;: "基于多目标静态模糊模型的分布式电源规划", 电网技术, no. 04 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236663A (en) * | 2023-11-14 | 2023-12-15 | 深圳前海橙色魔方信息技术有限公司 | Computer data analysis method and system based on artificial intelligence |
| CN117236663B (en) * | 2023-11-14 | 2024-03-05 | 深圳前海橙色魔方信息技术有限公司 | Computer data analysis method and system based on artificial intelligence |
| CN117424231A (en) * | 2023-12-14 | 2024-01-19 | 深圳市华星数字有限公司 | Energy-saving power distribution control system and method |
| CN117424231B (en) * | 2023-12-14 | 2024-03-15 | 深圳市华星数字有限公司 | Energy-saving power distribution control system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116914751B (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116914751B (en) | Intelligent power distribution control system | |
| CN110417015A (en) | Micro-capacitance sensor Multiobjective Optimal Operation method and system based on Model Predictive Control | |
| CN109165764A (en) | A kind of line loss calculation method of genetic algorithm optimization BP neural network | |
| CN113300380B (en) | Load curve segmentation-based power distribution network reactive power optimization compensation method | |
| CN107706932B (en) | A kind of energy method for optimizing scheduling based on dynamic self-adapting fuzzy logic controller | |
| CN110837915B (en) | Low-voltage load point prediction and probability prediction method for power system based on hybrid integrated deep learning | |
| Dong et al. | Applying the ensemble artificial neural network-based hybrid data-driven model to daily total load forecasting | |
| CN113141012B (en) | Power grid power flow regulation and control decision reasoning method | |
| Khairuddin et al. | A novel method for ATC computations in a large-scale power system | |
| CN118484666B (en) | Energy storage power station evaluation method and system for source network load multi-element application | |
| Zhao et al. | A fast and optimal smart home energy management system: State-space approximate dynamic programming | |
| CN114429248A (en) | Transformer apparent power prediction method | |
| CN104021315A (en) | Method for calculating station service power consumption rate of power station on basis of BP neutral network | |
| CN116865343B (en) | Model-free self-adaptive control method, device and medium for distributed photovoltaic power distribution network | |
| Kumar et al. | Load forecasting of Andhra Pradesh grid using PSO, DE algorithms | |
| Wang et al. | Prioritized sum-tree experience replay TD3 DRL-based online energy management of a residential microgrid | |
| CN113690930A (en) | NSGA-III algorithm-based medium and long term locating and sizing method for distributed photovoltaic power supply | |
| CN113033898A (en) | Electrical load prediction method and system based on K-means clustering and BI-LSTM neural network | |
| CN115513945A (en) | Distributed power supply management method based on Internet of things | |
| CN114048576B (en) | Intelligent control method for energy storage system for stabilizing power transmission section tide of power grid | |
| CN115001002A (en) | Optimal scheduling method and system for solving energy storage participation peak clipping and valley filling | |
| CN115118015A (en) | Platform district power supply stability monitoring system based on fuse terminal | |
| Khairudin et al. | Estimated use of electrical load using regression analysis and adaptive neuro fuzzy inference system | |
| CN114298429A (en) | Power distribution network scheme aided decision-making method, system, device and storage medium | |
| Yasin et al. | Optimal least squares support vector machines parameter selection in predicting the output of distributed generation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An intelligent distribution control system Granted publication date: 20231205 Pledgee: Qilu Bank Co.,Ltd. Jinan Science and Technology Innovation Financial Center Branch Pledgor: Jinan shunxinda Electric Power Technology Co.,Ltd. Registration number: Y2024980019103 |